Specifications

Publisher: IEEE Computer Society, 2001 L Street N.W., Suite 700, Washington, DC 20036-4928,
United States
Abstract: Human action recognition is a challenging filed in computer vision. In this paper, a
novel probabilistic graphical model, called topic-relative conditional random field(TCRF), is firstly
proposed. The model is constructed by adding a topic node and using a triangular-chain structure
in the top layer of the linear-chain conditional random field(LCRF) to overcome the drawback of
independent and identical distribution in LCRF. Then, we define a dynamic region for each action
and the discriminative features are extracted by using a hierarchical energy method. Lastly, two
popular probabilistic graphical models, HMM and LCRF, and the proposed TCRF model are
evaluated on our database, the experimental results show the effectiveness of the proposed
method. © 2012 IEEE.
Number of references: 23
Main heading: Random processes
Controlled terms: Artificial intelligence - Gesture recognition - Speech recognition
Uncontrolled terms: Conditional random field - Discriminative features - Dynamic region
- Energy method - Human-action recognition - Probabilistic graphical models - Top
layers
Classification code: 716 Telecommunication; Radar, Radio and Television - 723.4 Artificial
Intelligence - 723.5 Computer Applications - 922.1 Probability Theory
DOI: 10.1109/ICACI.2012.6463239
Database: Compendex
Compilation and indexing terms, © 2013 Elsevier Inc.
20130329 新增 11 条
1.
Accession number: 20131216133819
Title: An anti-counterfeiting method for printed image by digital halftoning method
Authors: Duan, Jinghong1 ; Zhang, Erhu2/段敬红;张二虎
Author affiliation: 1 School of Computer Science and Engineering, Xi'An University of
Technology, Xi'an, China
2 Department of Information Science, Xi'An University of Technology, Xi'an, China
Corresponding author: Duan, J.
Source title: 2012 5th International Congress on Image and Signal Processing, CISP 2012
Abbreviated source title: Int. Congr. Image Signal Process., CISP
Monograph title: 2012 5th International Congress on Image and Signal Processing, CISP 2012
Issue date: 2012
Publication year: 2012
Pages: 562-566
Article number: 6469758
Language: English
ISBN-13: 9781467309622
Document type: Conference article (CA)
Conference name: 2012 5th International Congress on Image and Signal Processing, CISP 2012
Conference date: October 16, 2012 - October 18, 2012